Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58438
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     అని
    -0.09
    raff
    -0.09
    悦
    -0.08
     outings
    -0.08
    �
    -0.08
     குறித்து
    -0.08
     вниз
    -0.08
     irratti
    -0.08
     பற்றி
    -0.08
     подел
    -0.07
    POSITIVE LOGITS
     punishment
    0.08
     cons
    0.07
    ូវ
    0.07
    来自
    0.07
     �
    0.07
     công
    0.07
     kou
    0.07
    _checker
    0.07
     Harrison
    0.06
     epit
    0.06
    Activations Density 0.048%

    No Known Activations